Haim Avron

Optimizing Spectral Sums using Randomized Chebyshev Expansions.

2018 · arXiv (Cornell University)

The trace of matrix functions, often called spectral sums, e.g., rank, log-determinant and nuclear norm, appear in many machine learning tasks. However, optimizing or computing such (parameterized) spectral sums typically involves the matrix decomposition at …